TSN Switch Queue Length Prediction Based on an Improved LSTM Network

With the high-speed development of network technology, time-sensitive networks (TSNs) are experiencing a phase of significant traffic growth. At the same time, they have to ensure that highly critical time-sensitive information can be transmitted in a timely and accurate manner. In the future, TSNs will have to further improve network throughput to meet the increasing traffic demand based on the guaranteed transmission delay. Therefore, an efficient route scheduling scheme is necessary to achieve network load balance and improve network throughput. A time-sensitive software-defined network (TSSDN) can address the highly distributed industrial Internet network infrastructure, which cannot be accomplished by traditional industrial communication technologies, and it can achieve distributed intelligent dynamic route scheduling of the network through global network monitoring. The prerequisite for intelligent dynamic scheduling is that the queue length of future switches can be accurately predicted so that dynamic route planning for flow can be performed based on the prediction results. To address the queue length prediction problem, we propose a TSN switch queue length prediction model based on the TSSDN architecture. The prediction process has three steps: network topology dimension reduction, feature selection, and training prediction. The principal component analysis (PCA) algorithm is used to reduce the dimensionality of the network topology to eliminate unnecessary redundancy and overlap of relevant information. Feature selection requires comprehensive consideration of the influencing factors that affect the switch queue length, such as time and network topology. The training prediction is performed with the help of our enhanced long short-term memory (LSTM) network. The input-output structure of the network is changed based on the extracted features to improve the prediction accuracy, thus predicting the network congestion caused by bursty traffic. Finally, the results of the simulation demonstrate that our proposed TSN switch queue length prediction model based on the improved LSTM network algorithm doubles the prediction accuracy compared to the original model because it considers more influencing factors as features in the neural network for training and learning.

Design of an 8X8 Optical Matrix Protection Device based on Electric Power Communication Network

In order to realize the fast establishment of power fiber circuitous channels, the reliability of power communication optical cable network is guaranteed. An optical matrix 8X8 protection device is designed by using all-optical switcher. The test results show that at the end of each input light path, any 8 paths can be switched, it can achieve 1:8 protection switch, realized the arbitrary switching of three modes and has the function of remote fiber route scheduling.

Enhanced Routing Schedule - Imbalanced Classification Algorithm for IOT based Software Defined Networks

Route scheduling optimization is important in SDN network. The SDN network needs the best solution for route optimization. Limited networking of software is the most interesting development in this field as it is important to provide a fast and reliable routing path based on its need. The IoT supports software defined applications interface in the overall networks. The SDN is recommended by enhancing the SDN architecture's benefits in improving research network quality. SDN network information exchange is one of the most important factor. It is important to plan the information accordingly and adjust a load of information to the SDN. A Maximum throughput scheduling process is proposed, which is upgraded using the Imbalanced Classification Algorithm. SDN has shown the advantage in many ways compared to the traditional network. But the problem of load inconstancy still occurs in SDN. The imbalanced classification method supports the maximum throughput schedule function and integrates load balancing strategies to improve SDN networks' Performance. Classification is to be proposed based on machine command in QoS. An imbalanced classification learning method is used for improving the QoS requirements and shows that the simulated results of the identified traffic load balance and maximum throughputs in the proposed solutions. Functionality has been improved much better than previous functions in the same area.